Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization Article Swipe
Yeji Song
,
Jimyeong Kim
,
Wonhark Park
,
Won Sik Shin
,
Wonjong Rhee
,
Nojun Kwak
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v39i19.34264
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v39i19.34264
In a surge of text-to-image (T2I) models and their customization methods that generate new images of a user-provided subject, current works focus on alleviating the costs incurred by a lengthy per-subject optimization. These zero-shot customization methods encode the image of a specified subject into a visual embedding which is then utilized alongside the textual embedding for diffusion guidance. The visual embedding incorporates intrinsic information about the subject, while the textual embedding provides a new context. However, the existing methods often 1) generate images with the same pose as an input image, and 2) exhibit deterioration in the subject's identity when facing a pose variation prompt. We first pin down the problem and show that redundant pose information in the visual embedding interferes with the pose indication in the textual embedding. Conversely, the textual embedding also harms the subject's identity which is tightly entangled with the pose in the visual embedding. As a remedy, we propose text-orthogonal visual embedding which effectively harmonizes with the given textual embedding. We also adopt the visual-only embedding and inject the subject's clear features utilizing a self-attention swap. Our method is both effective and robust, offering highly flexible zero-shot generation while effectively maintaining the subject's identity.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1609/aaai.v39i19.34264
- https://ojs.aaai.org/index.php/AAAI/article/download/34264/36419
- OA Status
- diamond
- References
- 8
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4409363494
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4409363494Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1609/aaai.v39i19.34264Digital Object Identifier
- Title
-
Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image CustomizationWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-04-11Full publication date if available
- Authors
-
Yeji Song, Jimyeong Kim, Wonhark Park, Won Sik Shin, Wonjong Rhee, Nojun KwakList of authors in order
- Landing page
-
https://doi.org/10.1609/aaai.v39i19.34264Publisher landing page
- PDF URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/34264/36419Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
diamondOpen access status per OpenAlex
- OA URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/34264/36419Direct OA link when available
- Concepts
-
Zero (linguistics), Personalization, Image (mathematics), Shot (pellet), Computer science, Computer graphics (images), Artificial intelligence, Information retrieval, World Wide Web, Linguistics, Materials science, Philosophy, MetallurgyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
8Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4409363494 |
|---|---|
| doi | https://doi.org/10.1609/aaai.v39i19.34264 |
| ids.doi | https://doi.org/10.1609/aaai.v39i19.34264 |
| ids.openalex | https://openalex.org/W4409363494 |
| fwci | 0.0 |
| type | article |
| title | Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization |
| biblio.issue | 19 |
| biblio.volume | 39 |
| biblio.last_page | 20557 |
| biblio.first_page | 20549 |
| topics[0].id | https://openalex.org/T10799 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.987500011920929 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1707 |
| topics[0].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[0].display_name | Data Visualization and Analytics |
| topics[1].id | https://openalex.org/T11439 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9552000164985657 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Video Analysis and Summarization |
| topics[2].id | https://openalex.org/T11165 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.939300000667572 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Image and Video Quality Assessment |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2780813799 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7563902735710144 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q3274237 |
| concepts[0].display_name | Zero (linguistics) |
| concepts[1].id | https://openalex.org/C183003079 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6402912735939026 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1000371 |
| concepts[1].display_name | Personalization |
| concepts[2].id | https://openalex.org/C115961682 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6095547676086426 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[2].display_name | Image (mathematics) |
| concepts[3].id | https://openalex.org/C2778344882 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5821518898010254 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q278938 |
| concepts[3].display_name | Shot (pellet) |
| concepts[4].id | https://openalex.org/C41008148 |
| concepts[4].level | 0 |
| concepts[4].score | 0.5146887898445129 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[4].display_name | Computer science |
| concepts[5].id | https://openalex.org/C121684516 |
| concepts[5].level | 1 |
| concepts[5].score | 0.3814515471458435 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q7600677 |
| concepts[5].display_name | Computer graphics (images) |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.37585389614105225 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C23123220 |
| concepts[7].level | 1 |
| concepts[7].score | 0.3357040286064148 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q816826 |
| concepts[7].display_name | Information retrieval |
| concepts[8].id | https://openalex.org/C136764020 |
| concepts[8].level | 1 |
| concepts[8].score | 0.2237834930419922 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q466 |
| concepts[8].display_name | World Wide Web |
| concepts[9].id | https://openalex.org/C41895202 |
| concepts[9].level | 1 |
| concepts[9].score | 0.165833979845047 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[9].display_name | Linguistics |
| concepts[10].id | https://openalex.org/C192562407 |
| concepts[10].level | 0 |
| concepts[10].score | 0.13882598280906677 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q228736 |
| concepts[10].display_name | Materials science |
| concepts[11].id | https://openalex.org/C138885662 |
| concepts[11].level | 0 |
| concepts[11].score | 0.08054223656654358 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[11].display_name | Philosophy |
| concepts[12].id | https://openalex.org/C191897082 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q11467 |
| concepts[12].display_name | Metallurgy |
| keywords[0].id | https://openalex.org/keywords/zero |
| keywords[0].score | 0.7563902735710144 |
| keywords[0].display_name | Zero (linguistics) |
| keywords[1].id | https://openalex.org/keywords/personalization |
| keywords[1].score | 0.6402912735939026 |
| keywords[1].display_name | Personalization |
| keywords[2].id | https://openalex.org/keywords/image |
| keywords[2].score | 0.6095547676086426 |
| keywords[2].display_name | Image (mathematics) |
| keywords[3].id | https://openalex.org/keywords/shot |
| keywords[3].score | 0.5821518898010254 |
| keywords[3].display_name | Shot (pellet) |
| keywords[4].id | https://openalex.org/keywords/computer-science |
| keywords[4].score | 0.5146887898445129 |
| keywords[4].display_name | Computer science |
| keywords[5].id | https://openalex.org/keywords/computer-graphics |
| keywords[5].score | 0.3814515471458435 |
| keywords[5].display_name | Computer graphics (images) |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.37585389614105225 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/information-retrieval |
| keywords[7].score | 0.3357040286064148 |
| keywords[7].display_name | Information retrieval |
| keywords[8].id | https://openalex.org/keywords/world-wide-web |
| keywords[8].score | 0.2237834930419922 |
| keywords[8].display_name | World Wide Web |
| keywords[9].id | https://openalex.org/keywords/linguistics |
| keywords[9].score | 0.165833979845047 |
| keywords[9].display_name | Linguistics |
| keywords[10].id | https://openalex.org/keywords/materials-science |
| keywords[10].score | 0.13882598280906677 |
| keywords[10].display_name | Materials science |
| keywords[11].id | https://openalex.org/keywords/philosophy |
| keywords[11].score | 0.08054223656654358 |
| keywords[11].display_name | Philosophy |
| language | en |
| locations[0].id | doi:10.1609/aaai.v39i19.34264 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4210191458 |
| locations[0].source.issn | 2159-5399, 2374-3468 |
| locations[0].source.type | conference |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2159-5399 |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| locations[0].source.host_organization | https://openalex.org/P4310320058 |
| locations[0].source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320058 |
| locations[0].license | |
| locations[0].pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/34264/36419 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| locations[0].landing_page_url | https://doi.org/10.1609/aaai.v39i19.34264 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5103100996 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-5436-5801 |
| authorships[0].author.display_name | Yeji Song |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yeji Song |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5037195485 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Jimyeong Kim |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Jimyeong Kim |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5111153023 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Wonhark Park |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Wonhark Park |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5008938526 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-6829-8825 |
| authorships[3].author.display_name | Won Sik Shin |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Wonsik Shin |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5056032525 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-2590-8774 |
| authorships[4].author.display_name | Wonjong Rhee |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Wonjong Rhee |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5084897975 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-1792-0327 |
| authorships[5].author.display_name | Nojun Kwak |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Nojun Kwak |
| authorships[5].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://ojs.aaai.org/index.php/AAAI/article/download/34264/36419 |
| open_access.oa_status | diamond |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10799 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.987500011920929 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1707 |
| primary_topic.subfield.display_name | Computer Vision and Pattern Recognition |
| primary_topic.display_name | Data Visualization and Analytics |
| related_works | https://openalex.org/W2074502265, https://openalex.org/W4214877189, https://openalex.org/W2773965352, https://openalex.org/W2381179799, https://openalex.org/W2980279061, https://openalex.org/W2334685461, https://openalex.org/W2366718574, https://openalex.org/W2359774528, https://openalex.org/W4298312966, https://openalex.org/W2325697621 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1609/aaai.v39i19.34264 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4210191458 |
| best_oa_location.source.issn | 2159-5399, 2374-3468 |
| best_oa_location.source.type | conference |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2159-5399 |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| best_oa_location.source.host_organization | https://openalex.org/P4310320058 |
| best_oa_location.source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310320058 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/34264/36419 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| best_oa_location.landing_page_url | https://doi.org/10.1609/aaai.v39i19.34264 |
| primary_location.id | doi:10.1609/aaai.v39i19.34264 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4210191458 |
| primary_location.source.issn | 2159-5399, 2374-3468 |
| primary_location.source.type | conference |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2159-5399 |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| primary_location.source.host_organization | https://openalex.org/P4310320058 |
| primary_location.source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320058 |
| primary_location.license | |
| primary_location.pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/34264/36419 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| primary_location.landing_page_url | https://doi.org/10.1609/aaai.v39i19.34264 |
| publication_date | 2025-04-11 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W4366330735, https://openalex.org/W4393178505, https://openalex.org/W4311001643, https://openalex.org/W4378473834, https://openalex.org/W4226182655, https://openalex.org/W4293342478, https://openalex.org/W4394673487, https://openalex.org/W4368304597 |
| referenced_works_count | 8 |
| abstract_inverted_index.a | 1, 16, 28, 40, 44, 72, 101, 151, 179 |
| abstract_inverted_index.1) | 80 |
| abstract_inverted_index.2) | 92 |
| abstract_inverted_index.As | 150 |
| abstract_inverted_index.In | 0 |
| abstract_inverted_index.We | 105, 166 |
| abstract_inverted_index.an | 88 |
| abstract_inverted_index.as | 87 |
| abstract_inverted_index.by | 27 |
| abstract_inverted_index.in | 95, 117, 126, 146 |
| abstract_inverted_index.is | 48, 140, 184 |
| abstract_inverted_index.of | 3, 15, 39 |
| abstract_inverted_index.on | 22 |
| abstract_inverted_index.we | 153 |
| abstract_inverted_index.Our | 182 |
| abstract_inverted_index.The | 58 |
| abstract_inverted_index.and | 7, 91, 111, 172, 187 |
| abstract_inverted_index.for | 55 |
| abstract_inverted_index.new | 13, 73 |
| abstract_inverted_index.pin | 107 |
| abstract_inverted_index.the | 24, 37, 52, 65, 68, 76, 84, 96, 109, 118, 123, 127, 131, 136, 144, 147, 162, 169, 174, 197 |
| abstract_inverted_index.also | 134, 167 |
| abstract_inverted_index.both | 185 |
| abstract_inverted_index.down | 108 |
| abstract_inverted_index.into | 43 |
| abstract_inverted_index.pose | 86, 102, 115, 124, 145 |
| abstract_inverted_index.same | 85 |
| abstract_inverted_index.show | 112 |
| abstract_inverted_index.that | 11, 113 |
| abstract_inverted_index.then | 49 |
| abstract_inverted_index.when | 99 |
| abstract_inverted_index.with | 83, 122, 143, 161 |
| abstract_inverted_index.(T2I) | 5 |
| abstract_inverted_index.These | 32 |
| abstract_inverted_index.about | 64 |
| abstract_inverted_index.adopt | 168 |
| abstract_inverted_index.clear | 176 |
| abstract_inverted_index.costs | 25 |
| abstract_inverted_index.first | 106 |
| abstract_inverted_index.focus | 21 |
| abstract_inverted_index.given | 163 |
| abstract_inverted_index.harms | 135 |
| abstract_inverted_index.image | 38 |
| abstract_inverted_index.input | 89 |
| abstract_inverted_index.often | 79 |
| abstract_inverted_index.surge | 2 |
| abstract_inverted_index.swap. | 181 |
| abstract_inverted_index.their | 8 |
| abstract_inverted_index.which | 47, 139, 158 |
| abstract_inverted_index.while | 67, 194 |
| abstract_inverted_index.works | 20 |
| abstract_inverted_index.encode | 36 |
| abstract_inverted_index.facing | 100 |
| abstract_inverted_index.highly | 190 |
| abstract_inverted_index.image, | 90 |
| abstract_inverted_index.images | 14, 82 |
| abstract_inverted_index.inject | 173 |
| abstract_inverted_index.method | 183 |
| abstract_inverted_index.models | 6 |
| abstract_inverted_index.visual | 45, 59, 119, 148, 156 |
| abstract_inverted_index.current | 19 |
| abstract_inverted_index.exhibit | 93 |
| abstract_inverted_index.lengthy | 29 |
| abstract_inverted_index.methods | 10, 35, 78 |
| abstract_inverted_index.problem | 110 |
| abstract_inverted_index.prompt. | 104 |
| abstract_inverted_index.propose | 154 |
| abstract_inverted_index.remedy, | 152 |
| abstract_inverted_index.robust, | 188 |
| abstract_inverted_index.subject | 42 |
| abstract_inverted_index.textual | 53, 69, 128, 132, 164 |
| abstract_inverted_index.tightly | 141 |
| abstract_inverted_index.However, | 75 |
| abstract_inverted_index.context. | 74 |
| abstract_inverted_index.existing | 77 |
| abstract_inverted_index.features | 177 |
| abstract_inverted_index.flexible | 191 |
| abstract_inverted_index.generate | 12, 81 |
| abstract_inverted_index.identity | 98, 138 |
| abstract_inverted_index.incurred | 26 |
| abstract_inverted_index.offering | 189 |
| abstract_inverted_index.provides | 71 |
| abstract_inverted_index.subject, | 18, 66 |
| abstract_inverted_index.utilized | 50 |
| abstract_inverted_index.alongside | 51 |
| abstract_inverted_index.diffusion | 56 |
| abstract_inverted_index.effective | 186 |
| abstract_inverted_index.embedding | 46, 54, 60, 70, 120, 133, 157, 171 |
| abstract_inverted_index.entangled | 142 |
| abstract_inverted_index.guidance. | 57 |
| abstract_inverted_index.identity. | 199 |
| abstract_inverted_index.intrinsic | 62 |
| abstract_inverted_index.redundant | 114 |
| abstract_inverted_index.specified | 41 |
| abstract_inverted_index.subject's | 97, 137, 175, 198 |
| abstract_inverted_index.utilizing | 178 |
| abstract_inverted_index.variation | 103 |
| abstract_inverted_index.zero-shot | 33, 192 |
| abstract_inverted_index.embedding. | 129, 149, 165 |
| abstract_inverted_index.generation | 193 |
| abstract_inverted_index.harmonizes | 160 |
| abstract_inverted_index.indication | 125 |
| abstract_inverted_index.interferes | 121 |
| abstract_inverted_index.Conversely, | 130 |
| abstract_inverted_index.alleviating | 23 |
| abstract_inverted_index.effectively | 159, 195 |
| abstract_inverted_index.information | 63, 116 |
| abstract_inverted_index.maintaining | 196 |
| abstract_inverted_index.per-subject | 30 |
| abstract_inverted_index.visual-only | 170 |
| abstract_inverted_index.incorporates | 61 |
| abstract_inverted_index.customization | 9, 34 |
| abstract_inverted_index.deterioration | 94 |
| abstract_inverted_index.optimization. | 31 |
| abstract_inverted_index.text-to-image | 4 |
| abstract_inverted_index.user-provided | 17 |
| abstract_inverted_index.self-attention | 180 |
| abstract_inverted_index.text-orthogonal | 155 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile.value | 0.14159292 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |